Grok 4.20 Non-Reasoning API Pricing: High-Throughput 2M Execution
Explore xAI Grok 4.20 Non-Reasoning API pricing ($2.00/M input, $6.00/M output), fast streaming throughput, 2M context scale, and live search integration.
Full specs, context window and API limits →How much does Grok-4.20 cost per million tokens?
xAI Grok 4.20 Non-Reasoning charges $2.00 per million input tokens and $6.00 per million output tokens ($3.00/M blended at 3:1). Provides high generation speed without reasoning token overhead. Verified 2026-09-08.
Verified 2026-09-07 — source
How much does Grok-4.20 cost per 1,000 requests?
Computed from generated token pricing. Each row assumes the listed input and output tokens per request; this model has no measured verbosity factor, so the unadjusted output estimate is shown.
| Request shape | Input tokens | Output tokens | Cost / 1,000 requests |
|---|---|---|---|
| Short | 100 | 50 | $0.5000 |
| Medium | 1,000 | 500 | $5.0000 |
| Long | 4,000 | 2,000 | $20.0000 |
Formula: ((input price × input tokens) + (output price × output tokens × verbosity factor)) ÷ 1,000,000 × 1,000. Assumptions: short 100/50, medium 1,000/500, long 4,000/2,000 input/output tokens per request. Unadjusted — no measured verbosity factor is available.
Three model-specific pricing decisions
This page owns the fast non-reasoning workload surface. The paired reasoning route owns hidden/output expansion; equal listed rates do not erase that different output assumption.
1. Chat, document, and multimodal-shaped bills
| Workload | Input / output assumption | Non-reasoning / 100K | Paired reasoning / 100K |
|---|---|---|---|
| Chat | 1,000 / 300 | $380.00 | $560.00 |
| Document | 8,000 / 800 | $2080.00 | $2560.00 |
| Multimodal-shaped | 4,000 text / 500 output | $1100.00 | Image unit unavailable; output expansion proxy only |
2. Latency/retry-adjusted cost per accepted response
| Shape | Base / 100K | Speed evidence | Accepted-response cost |
|---|---|---|---|
| Chat | $380.00 | 104 tokens/sec | Retry rate unavailable — no adjusted result |
| Document | $2080.00 | 104 tokens/sec | Unavailable — use base ÷ (1 − retry rate) |
3. Mechanics evidence matrix
| Dimension | Sourced value | Safe boundary |
|---|---|---|
| Context | Unavailable | Do not infer a tier |
| Image unit | Unavailable | Do not convert text tokens |
| Cache / batch | Unavailable | Not free by default |
| Rate limit | Unavailable | Provider policy remains elsewhere |
Verified 2026-04-06. Luna is the data owner for this server-rendered module. “Unavailable” means no compatible dated evidence was found; it is never treated as zero. First-party price source · Run this exact scenario.
All three decisions are server-rendered for Grok-4.20; fixed inputs, formulas, dated sources, and unavailable states are intentionally visible.
Batch 67 · exact model pricing decision contributions · verified 2026-09-07
Exact model boundary: xAI grok-4.20-0309-non-reasoning (slug grok-4-20-0309-non-reasoning). First-party provider pricing and API documentation remain fact owners.
Token pricing and high-throughput workload monthly spend board
Frozen Batch 67 scenario board. Formula / deterministic rule: monthly_spend = calls * ((in_tokens * 2.00 + out_tokens * 6.00) / 1M) Boundary: Owns base token tariff comparisons and workload expenditure modeling.
| Frozen scenario / field ID | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
batch67-grok-4-20-0309-non-reasoning-m1-r120K interactive customer queries | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=20K interactive customer queries; workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — 20K interactive customer queries is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m1-r250K automated text generations | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=50K automated text generations; workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — 50K automated text generations is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m1-r3100K data classification passes | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=100K data classification passes; workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — 100K data classification passes is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m1-r4prompt caching active (75% read discount) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=prompt caching active (75% read discount); workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — prompt caching active (75% read discount) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m1-r5batch processing active (50% both) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=batch processing active (50% both); workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — batch processing active (50% both) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m1-r6unresolved pricing currency | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=unresolved pricing currency; workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — unresolved pricing currency has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: xAI Grok developer pricing; verification date 2026-09-07. Missing or conflicting joins fail closed.
Turnaround time latency and interactive UX SLA audit
Frozen Batch 67 scenario board. Formula / deterministic rule: turnaround = ttft + (tokens_out / tps); optimized for immediate response streaming Boundary: Owns turnaround time benchmarks and user experience responsiveness.
| Frozen scenario / field ID | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
batch67-grok-4-20-0309-non-reasoning-m2-r1real-time conversational streaming (<150ms) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=real-time conversational streaming (<150ms); task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — real-time conversational streaming (<150ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m2-r2customer support intent routing (<300ms) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=customer support intent routing (<300ms); task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — customer support intent routing (<300ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m2-r3automated article drafting | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=automated article drafting; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — automated article drafting is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m2-r4batch document parsing queue | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=batch document parsing queue; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — batch document parsing queue is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m2-r5concurrency contention latency spike | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=concurrency contention latency spike; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — concurrency contention latency spike is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m2-r6unmeasured speed fixture | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=unmeasured speed fixture; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — unmeasured speed fixture is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
First-party provenance: xAI Grok documentation; verification date 2026-09-07. Missing or conflicting joins fail closed.
Context window saturation (2M scale) capability gate
Frozen Batch 67 scenario board. Formula / deterministic rule: eligible = (context <= 2M ? Eligible : Excluded); massive context ingestion Boundary: Owns context scaling and capability gating for large inputs.
| Frozen scenario / field ID | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
batch67-grok-4-20-0309-non-reasoning-m3-r1short text query (5K tokens) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=short text query (5K tokens); context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — short text query (5K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m3-r2large legal contract (100K tokens) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=large legal contract (100K tokens); context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — large legal contract (100K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m3-r3monolithic application codebase (500K tokens) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=monolithic application codebase (500K tokens); context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — monolithic application codebase (500K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m3-r4full system archive (1.5M tokens) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=full system archive (1.5M tokens); context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — full system archive (1.5M tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m3-r52M full context saturation test | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=2M full context saturation test; context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — 2M full context saturation test is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch67-grok-4-20-0309-non-reasoning-m3-r6unsupported media payload format | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=unsupported media payload format; context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-07; measurement versus assumption=explicit | Unavailable — unsupported media payload format has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: xAI Grok documentation; verification date 2026-09-07. Missing or conflicting joins fail closed.
Method and limitations: formulas are deterministic; observed and assumed inputs are labeled; no missing provider, host, account, region, realm, alias, snapshot, revision, weight, artifact, control, tool, modality, workload, rate-period, timestamp, or result is transferred. Run the grok-4-20-0309-non-reasoning Batch 67 scenario →
Batch 75 Verified Model Pricing Intelligence•Model owner: grok-4-20-0309-non-reasoning (xAI)•Audit date: 2026-09-08
Grok 4.20 Non-Reasoning API Pricing: High-Throughput 2M Execution
xAI Grok 4.20 Non-Reasoning charges $2.00 per million input tokens and $6.00 per million output tokens ($3.00/M blended at 3:1). Provides high generation speed without reasoning token overhead. Verified 2026-09-08.
Token pricing and high-throughput workload monthly spend board
Frozen Batch 75 scenario board. Formula / deterministic rule: monthly_spend = calls * ((in_tokens * 2.00 + out_tokens * 6.00) / 1M) Boundary: Owns base token tariff comparisons and workload expenditure modeling.
| Frozen scenario / field ID | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
batch75-grok-4-20-0309-non-reasoning-m1-r120K interactive customer queries | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=20K interactive customer queries; workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 20K interactive customer queries is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m1-r250K automated text generations | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=50K automated text generations; workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 50K automated text generations is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m1-r3100K data classification passes | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=100K data classification passes; workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 100K data classification passes is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m1-r4prompt caching active (75% read discount) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=prompt caching active (75% read discount); workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — prompt caching active (75% read discount) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m1-r5batch processing active (50% both) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=batch processing active (50% both); workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — batch processing active (50% both) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m1-r6unresolved pricing currency | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=unresolved pricing currency; workload; prompt tokens; completion tokens; standard spend; cached spend; cost winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unresolved pricing currency has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: xAI Grok developer pricing; verification date 2026-09-08. Missing or conflicting joins fail closed.
Turnaround time latency and interactive UX SLA audit
Frozen Batch 75 scenario board. Formula / deterministic rule: turnaround = ttft + (tokens_out / tps); optimized for immediate response streaming Boundary: Owns turnaround time benchmarks and user experience responsiveness.
| Frozen scenario / field ID | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
batch75-grok-4-20-0309-non-reasoning-m2-r1real-time conversational streaming (<150ms) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=real-time conversational streaming (<150ms); task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — real-time conversational streaming (<150ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m2-r2customer support intent routing (<300ms) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=customer support intent routing (<300ms); task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — customer support intent routing (<300ms) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m2-r3automated article drafting | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=automated article drafting; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — automated article drafting is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m2-r4batch document parsing queue | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=batch document parsing queue; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — batch document parsing queue is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m2-r5concurrency contention latency spike | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=concurrency contention latency spike; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — concurrency contention latency spike is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m2-r6unmeasured speed fixture | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=unmeasured speed fixture; task; response SLA; TTFT; generation speed; SLA compliance; responsiveness winner; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unmeasured speed fixture is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
First-party provenance: xAI Grok documentation; verification date 2026-09-08. Missing or conflicting joins fail closed.
Context window saturation (2M scale) capability gate
Frozen Batch 75 scenario board. Formula / deterministic rule: eligible = (context <= 2M ? Eligible : Excluded); massive context ingestion Boundary: Owns context scaling and capability gating for large inputs.
| Frozen scenario / field ID | Model, identity, provider, and evidence fields | Result | State |
|---|---|---|---|
batch75-grok-4-20-0309-non-reasoning-m3-r1short text query (5K tokens) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=short text query (5K tokens); context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — short text query (5K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m3-r2large legal contract (100K tokens) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=large legal contract (100K tokens); context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — large legal contract (100K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m3-r3monolithic application codebase (500K tokens) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=monolithic application codebase (500K tokens); context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — monolithic application codebase (500K tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m3-r4full system archive (1.5M tokens) | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=full system archive (1.5M tokens); context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — full system archive (1.5M tokens) is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m3-r52M full context saturation test | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=2M full context saturation test; context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — 2M full context saturation test is a frozen fixture pending exact identity, configuration, and denominator joins. | UNTESTED — assumption cannot establish a verdict |
batch75-grok-4-20-0309-non-reasoning-m3-r6unsupported media payload format | model=grok-4.20-0309-non-reasoning; slug=grok-4-20-0309-non-reasoning; provider=xAI; scenario=unsupported media payload format; context size; codebase eligible; prompt cost; completion cost; context gate verdict; prompt/config/input/output/result/cache/checkpoint/artifact hashes=required; evidence=2026-09-08; measurement versus assumption=explicit | Unavailable — unsupported media payload format has no matched, dated bilateral observation. | FAIL CLOSED — manual, probe, or source evidence required |
First-party provenance: xAI Grok documentation; verification date 2026-09-08. Missing or conflicting joins fail closed.
How fast is Grok-4.20?
Tokens / sec
104
TTFT
290 ms
Rank
#16 of 31
$ / M ÷ t/s
$0.03
Measured with 5 runs on a fixed prompt — see the full methodology.
How much does Grok-4.20 cost at scale?
| Tokens / month | Est. cost (blended 3:1) |
|---|---|
| 100,000 | $0.30 |
| 1,000,000 | $3.00 |
| 10,000,000 | $30.00 |
| 100,000,000 | $300.00 |
How does Grok-4.20 compare with other models?
Grok-3 Mini — $0.26/MGrok 4.3 — $1.56/MGrok-3 — $2.50/MGrok-4.20 Reasoning — $3.00/MGrok 4.6 — $3.00/MGrok-4.20 Reasoning — $3.00/MGrok 4.6 — $3.00/MGrok 4.5 — $3.00/M
What is Grok-4.20 best for?
What should you explore next for Grok-4.20?
Looking for a cheaper option?
Ministral 8B is 95% cheaper — a config migration. See all 8 alternatives to Grok-4.20 →
What are common questions about Grok-4.20?
Is Grok-4.20 cheaper than Grok-4.20 Reasoning?
Grok-4.20 costs $3.00/M blended tokens, Grok-4.20 Reasoning costs $3.00/M — Grok-4.20 Reasoning is cheaper.
How much does 1 million tokens cost with Grok-4.20?
At a 3:1 input:output ratio, 1 million blended tokens costs approximately $3.00. Pure input costs $2.00/M; pure output costs $6.00/M.
What does Grok-4.20 cost at high volume?
At 100 million blended tokens a month, Grok-4.20 costs approximately $300.00. See the cost-at-scale table below for other volumes.