Side-by-side comparison · models
GPT-6 Astra vs gpt-oss-120b (free)
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
GPT-6 Astra
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.
Models
gpt-oss-120b (free)
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.
Checked facts
Line by line
| Measure | GPT-6 Astra | gpt-oss-120b (free) |
|---|---|---|
| Input price | $10.00 per million tokens | Not checked yet |
| Output price | $50.00 per million tokens | Not checked yet |
| Price on amazon-bedrock | $1.00 per million cached input tokens | Not checked yet |
| Price on amazon-bedrock | $10.00 per million input tokens | $0.150 per million input tokens |
| Price on amazon-bedrock | $50.00 per million output tokens | $0.600 per million output tokens |
| Price on azure | $1.00 per million cached input tokens | Not checked yet |
| Price on azure | $10.00 per million input tokens | Not checked yet |
| Price on azure | $50.00 per million output tokens | Not checked yet |
| Price on openai | $0.500 per million cached input tokens | Not checked yet |
| Price on openai | $5.00 per million input tokens | Not checked yet |
| Price on openai | $25.00 per million output tokens | Not checked yet |
| Price on akashml | Not checked yet | $0.030 per million cached input tokens |
| Price on akashml | Not checked yet | $0.030 per million input tokens |
| Price on akashml | Not checked yet | $0.187 per million output tokens |
| Price on baseten | Not checked yet | $0.100 per million cached input tokens |
| Price on baseten | Not checked yet | $0.100 per million input tokens |
| Price on baseten | Not checked yet | $0.500 per million output tokens |
| Price on cerebras | Not checked yet | $0.350 per million cached input tokens |
| Price on cerebras | Not checked yet | $0.350 per million input tokens |
| Price on cerebras | Not checked yet | $0.750 per million output tokens |
| Price on coreweave | Not checked yet | $0.030 per million cached input tokens |
| Price on coreweave | Not checked yet | $0.030 per million input tokens |
| Price on coreweave | Not checked yet | $0.170 per million output tokens |
| Price on crusoe | Not checked yet | $0.050 per million cached input tokens |
| Price on crusoe | Not checked yet | $0.050 per million input tokens |
| Price on crusoe | Not checked yet | $0.250 per million output tokens |
| Price on deepinfra | Not checked yet | $0.037 per million input tokens |
| Price on deepinfra | Not checked yet | $0.170 per million output tokens |
| Price on dekallm | Not checked yet | $0.030 per million cached input tokens |
| Price on dekallm | Not checked yet | $0.030 per million input tokens |
| Price on dekallm | Not checked yet | $0.180 per million output tokens |
| Price on digitalocean | Not checked yet | $0.012 per million cached input tokens |
| Price on digitalocean | Not checked yet | $0.060 per million input tokens |
| Price on digitalocean | Not checked yet | $0.420 per million output tokens |
| Price on google-vertex | Not checked yet | $0.090 per million input tokens |
| Price on google-vertex | Not checked yet | $0.360 per million output tokens |
| Price on groq | Not checked yet | $0.075 per million cached input tokens |
| Price on groq | Not checked yet | $0.150 per million input tokens |
| Price on groq | Not checked yet | $0.600 per million output tokens |
| Price on io-net | Not checked yet | $0.015 per million cached input tokens |
| Price on io-net | Not checked yet | $0.030 per million input tokens |
| Price on io-net | Not checked yet | $0.150 per million output tokens |
| Price on mancer | Not checked yet | $0.055 per million cached input tokens |
| Price on mancer | Not checked yet | $0.055 per million input tokens |
| Price on mancer | Not checked yet | $0.250 per million output tokens |
| Price on mara | Not checked yet | $0.150 per million input tokens |
| Price on mara | Not checked yet | $0.750 per million output tokens |
| Price on near-ai | Not checked yet | $0.015 per million cached input tokens |
| Price on near-ai | Not checked yet | $0.030 per million input tokens |
| Price on near-ai | Not checked yet | $0.150 per million output tokens |
| Price on nebius | Not checked yet | $0.100 per million cached input tokens |
| Price on nebius | Not checked yet | $0.150 per million input tokens |
| Price on nebius | Not checked yet | $0.600 per million output tokens |
| Price on novita | Not checked yet | $0.050 per million input tokens |
| Price on novita | Not checked yet | $0.250 per million output tokens |
| Price on parasail | Not checked yet | $0.055 per million cached input tokens |
| Price on parasail | Not checked yet | $0.100 per million input tokens |
| Price on parasail | Not checked yet | $0.750 per million output tokens |
| Price on phala | Not checked yet | $0.150 per million input tokens |
| Latest version | openai/gpt-6-astra-20260903 | openai/gpt-oss-120b |
| Time to first token (ms) | 337,140 | 810 |
| Time to first token (ms) on amazon-bedrock | 2,934 | 517 |
| Time to first token (ms) on azure | 5,939 | Not checked yet |
| Time to first token (ms) on openai | 15,597 | Not checked yet |
| Output speed (tokens a second) | 53.2 | 210.3 |
| Output speed (tokens a second) on amazon-bedrock | 56.5 | 202 |
| Output speed (tokens a second) on azure | 36 | Not checked yet |
| Output speed (tokens a second) on openai | 12 | Not checked yet |
| Time to first token (ms) on akashml | Not checked yet | 548 |
| Time to first token (ms) on baseten | Not checked yet | 180 |
| Time to first token (ms) on cerebras | Not checked yet | 228 |
| Time to first token (ms) on coreweave | Not checked yet | 277 |
| Time to first token (ms) on crusoe | Not checked yet | 331 |
| Time to first token (ms) on deepinfra | Not checked yet | 501 |
| Time to first token (ms) on dekallm | Not checked yet | 501 |
| Time to first token (ms) on digitalocean | Not checked yet | 570 |
| Time to first token (ms) on google-vertex | Not checked yet | 2,313 |
| Time to first token (ms) on groq | Not checked yet | 240 |
| Time to first token (ms) on io-net | Not checked yet | 847 |
| Time to first token (ms) on mancer | Not checked yet | 595 |
| Time to first token (ms) on mara | Not checked yet | 1,159 |
| Time to first token (ms) on near-ai | Not checked yet | 599 |
| Time to first token (ms) on nebius | Not checked yet | 228 |
| Time to first token (ms) on novita | Not checked yet | 832 |
| Time to first token (ms) on parasail | Not checked yet | 472 |
| Time to first token (ms) on phala | Not checked yet | 969 |
| Time to first token (ms) on prime-intellect | Not checked yet | 772 |
| Time to first token (ms) on sail-research | Not checked yet | 1,064 |
| Time to first token (ms) on sambanova | Not checked yet | 816 |
| Time to first token (ms) on siliconflow | Not checked yet | 1,035 |
| Time to first token (ms) on together | Not checked yet | 183 |
| Time to first token (ms) on venice | Not checked yet | 799 |
| Output speed (tokens a second) on akashml | Not checked yet | 59 |
| Output speed (tokens a second) on baseten | Not checked yet | 140 |
| Output speed (tokens a second) on cerebras | Not checked yet | 604 |
| Output speed (tokens a second) on coreweave | Not checked yet | 82 |
| Output speed (tokens a second) on crusoe | Not checked yet | 149 |
| Output speed (tokens a second) on deepinfra | Not checked yet | 27 |
| Output speed (tokens a second) on dekallm | Not checked yet | 48 |
| Output speed (tokens a second) on digitalocean | Not checked yet | 30 |
| Output speed (tokens a second) on google-vertex | Not checked yet | 50 |
| Output speed (tokens a second) on groq | Not checked yet | 301 |
| Output speed (tokens a second) on io-net | Not checked yet | 40 |
| Output speed (tokens a second) on mancer | Not checked yet | 106.5 |
| Tokens served on OpenRouter in a day | 46.1B (for 10 Nov 2026) | Not checked yet |
| Tool calls on OpenRouter in a day | 573.7K (for 10 Nov 2026) | Not checked yet |
| Artificial Analysis Intelligence Index | 56.9 | Not checked yet |
| Artificial Analysis Coding Index | 77.1 | Not checked yet |
| Artificial Analysis Agentic Index | 51 | Not checked yet |
| LMArena text rating (Elo) | 1,440 | Not checked yet |
| LMArena web development rating (Elo) | 1,764 | Not checked yet |
| LMArena vision rating (Elo) | 1,279 | Not checked yet |
| Gpqa diamond | 95.8% (for 3 Sept 2026) | 75.8% (for 5 Aug 2025) |
| Frontiermath tiers 1 3 v2 private | 93.7% (for 3 Sept 2026) | Not checked yet |
| Simpleqa verified | 75.6% (for 3 Sept 2026) | Not checked yet |
| Arc agi 2 | 95% (for 3 Sept 2026) | Not checked yet |
| Apex agents | 64.7% (for 3 Sept 2026) | 4.4% (for 5 Aug 2025) |
| Arc agi | 98.5% (for 3 Sept 2026) | Not checked yet |
| Balrog | 68.3% (for 3 Sept 2026) | Not checked yet |
| Chess puzzles | 76% (for 3 Sept 2026) | Not checked yet |
| Dtbench | 97.3% (for 3 Sept 2026) | 76.3% (for 5 Aug 2025) |
| Ebr bench | 76.2% (for 3 Sept 2026) | Not checked yet |
| Frontiercode | 53.3% (for 3 Sept 2026) | Not checked yet |
| Frontiermath tier 4 v2 private | 97.6% (for 3 Sept 2026) | Not checked yet |
| Frontierswe | 65.5% (for 3 Sept 2026) | Not checked yet |
| Furniture assembly | 80% (for 3 Sept 2026) | Not checked yet |
| Gso bench | 79.4% (for 3 Sept 2026) | Not checked yet |
| Lmca | 64.4% (for 3 Sept 2026) | 22.1% (for 5 Aug 2025) |
| Mirrorcode | 46.7% (for 3 Sept 2026) | Not checked yet |
| Mystery game puzzles | 84% (for 3 Sept 2026) | 2% (for 5 Aug 2025) |
| Proofbench | 99% (for 3 Sept 2026) | Not checked yet |
| Remote labor index | 20.8% (for 3 Sept 2026) | Not checked yet |
| Spireclimb | 25.7% (for 3 Sept 2026) | Not checked yet |
| Weirdml | 93.6% (for 3 Sept 2026) | 48.2% (for 5 Aug 2025) |
| Weirdml v3 | 54% (for 3 Sept 2026) | Not checked yet |
| Otis mock aime 2024 2025 | 100% (saturated benchmark: the top models all score near the ceiling) (for 3 Sept 2026) | 88.9% (saturated benchmark: the top models all score near the ceiling) (for 5 Aug 2025) |
| Terminal bench | Not checked yet | 18.7% (for 5 Aug 2025) |
| Aider polyglot | Not checked yet | 41.8% (for 5 Aug 2025) |
| Fiction livebench | Not checked yet | 44.4% (for 5 Aug 2025) |
| Lech mazur writing | Not checked yet | 77.1% (for 5 Aug 2025) |
| Metr time horizons | Not checked yet | 56.6% (for 5 Aug 2025) |
| Simplebench | Not checked yet | 22.1% (for 5 Aug 2025) |
| Surface evolver bench | Not checked yet | 25% (for 5 Aug 2025) |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.